{ "openapi": "3.0.1", "info": { "title": "CSV & Excel Data Quality Cleaner", "description": "Clean CSV and Excel files under explicit rules, normalize columns and values, flag or remove duplicates, and export cleaned rows plus a structured validation report.", "version": "0.1", "x-build-id": "fQ01DnRvsFdTAOcnd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~csv-excel-data-quality-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-csv-excel-data-quality-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~csv-excel-data-quality-cleaner/runs": { "post": { "operationId": "runs-sync-automation-lab-csv-excel-data-quality-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~csv-excel-data-quality-cleaner/run-sync": { "post": { "operationId": "run-sync-automation-lab-csv-excel-data-quality-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "csvText": { "title": "Inline CSV", "type": "string", "description": "CSV text including a header row. Provide this or File URL, but not both." }, "fileUrl": { "title": "CSV or XLSX file URL", "pattern": "^https?://", "type": "string", "description": "Public HTTP(S) URL of one CSV or Excel .xlsx file (maximum 25 MB). Provide this or Inline CSV, but not both." }, "format": { "title": "File format", "enum": [ "auto", "csv", "xlsx" ], "type": "string", "description": "Detect the format automatically or force CSV/XLSX parsing.", "default": "auto" }, "sheetName": { "title": "Excel sheet name", "type": "string", "description": "Optional worksheet name. The first sheet is used when omitted." }, "normalizeColumnNames": { "title": "Normalize column names", "type": "boolean", "description": "Convert headers to lowercase snake_case and make duplicate headers unique.", "default": true }, "trimWhitespace": { "title": "Trim text whitespace", "type": "boolean", "description": "Remove leading and trailing whitespace from text values.", "default": true }, "emptyAsNull": { "title": "Convert empty values to null", "type": "boolean", "description": "Represent empty cells consistently as null.", "default": true }, "columnRules": { "title": "Column conversion and validation rules", "type": "array", "description": "Rules are matched after header normalization. Configure output names, types, required values, numeric ranges, patterns, or allowed values.", "items": { "type": "object", "required": [ "column" ], "properties": { "column": { "type": "string", "title": "Input column", "description": "Source column name after optional header normalization." }, "outputName": { "type": "string", "title": "Output column", "description": "Optional replacement name for this output column." }, "type": { "type": "string", "title": "Data type", "description": "Target value type.", "enum": [ "string", "number", "integer", "boolean", "date" ] }, "required": { "type": "boolean", "title": "Required", "description": "Whether an empty value creates a validation finding." }, "min": { "type": "number", "title": "Minimum", "description": "Optional minimum for numeric values." }, "max": { "type": "number", "title": "Maximum", "description": "Optional maximum for numeric values." }, "pattern": { "type": "string", "title": "Regular expression", "description": "Optional JavaScript regular expression for string validation." } } }, "default": [] }, "deduplicateBy": { "title": "Duplicate key columns", "type": "array", "description": "Columns whose combined values identify duplicate rows. Leave empty to disable duplicate detection.", "items": { "type": "string" }, "default": [] }, "duplicateAction": { "title": "Duplicate action", "enum": [ "flag", "remove", "keep" ], "type": "string", "description": "Flag duplicates in output, remove later duplicates, or keep them without removal (duplicate metadata is still included).", "default": "flag" }, "caseInsensitiveDuplicates": { "title": "Case-insensitive duplicate matching", "type": "boolean", "description": "Treat text values that differ only by letter case as the same duplicate key.", "default": true }, "maxRows": { "title": "Maximum rows", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of data rows to read after the header.", "default": 10000 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }